feat: 结题报告初稿助手首版 v1.0.1（draft-closing-report-default）

examples/real_browser_rpa/scripts/service/account_client.py

@@ -0,0 +1,355 @@
+"""account-manager CLI 集成（仅 subprocess，不 import 兄弟 skill 内部模块）。
+
+业务首启默认 ``ensure-web``（有则用、无则 add-web）；登记 ≠ 站点已登录。
+"""
+
+from __future__ import annotations
+
+import json
+import logging
+import os
+import subprocess
+import sys
+from typing import Any, Dict, List, Optional, Tuple
+
+from jiangchang_skill_core import config
+from jiangchang_skill_core.runtime_env import get_sibling_skills_root
+
+from util.constants import LEASE_HOLDER, LEASE_TTL_SEC, TARGET_PLATFORM
+from util.logging import mask_text
+
+logger = logging.getLogger(__name__)
+
+PLACEHOLDER_PLATFORM = TARGET_PLATFORM
+
+ACCOUNT_SETUP_MESSAGE = (
+    f"未能取得可用的 {PLACEHOLDER_PLATFORM} 账号（ensure-web 失败），所以还没有打开浏览器。"
+    f"请确认已安装 account-manager，并检查 platform={PLACEHOLDER_PLATFORM} 账号状态后重试。"
+)
+
+LEASE_BUSY_MESSAGE = (
+    "该平台下已有账号，但均被其他任务占用。请稍后重试或释放租约；不会自动新建账号。"
+)
+
+DEFAULT_AUTH_STRATEGY = "qr_code_manual"
+DEFAULT_ACCOUNT_LABEL = f"{PLACEHOLDER_PLATFORM} 默认"
+DEFAULT_START_URL = "https://www.example.com/"
+
+
+class AccountManagerError(Exception):
+    def __init__(self, code: str, message: str) -> None:
+        super().__init__(message)
+        self.code = code
+        self.message = message
+
+
+def mask_login_id(login_id: str) -> str:
+    return mask_text(login_id)
+
+
+def format_account_label(account: dict) -> str:
+    """人读账号标识：优先 login_id / 备注，最后才用数字 id。"""
+    for key in ("login_id", "account_label", "label"):
+        v = account.get(key)
+        if v is not None and str(v).strip():
+            return str(v).strip()
+    for key in ("id", "account_id"):
+        v = account.get(key)
+        if v is not None and str(v).strip():
+            return str(v).strip()
+    return ""
+
+
+def _is_placeholder_config(raw: str) -> bool:
+    s = (raw or "").strip()
+    if not s:
+        return True
+    if s.startswith("#"):
+        return True
+    low = s.lower()
+    if low in ("default-account", "none", "null", "n/a", "-"):
+        return True
+    return False
+
+
+def resolve_account_selectors_from_config() -> Tuple[Optional[str], Optional[str]]:
+    """从配置解析 (account_id, login_id)。
+
+    - ``DEFAULT_ACCOUNT_ID``：仅纯数字视为账号主键；其它非空非占位当作 login_id
+    - ``DEFAULT_LOGIN_ID``：手机号/用户名（可覆盖上一项推导的 login_id）
+    - 两者皆空：返回 (None, None) → 调用方走按平台 ensure-web
+    """
+    account_id: Optional[str] = None
+    login_id: Optional[str] = None
+
+    aid_raw = (config.get("DEFAULT_ACCOUNT_ID") or "").strip()
+    if not _is_placeholder_config(aid_raw):
+        if aid_raw.isdigit():
+            account_id = aid_raw
+        else:
+            login_id = aid_raw
+            logger.info("default_account_id_treated_as_login_id value=%s", aid_raw)
+
+    lid_raw = (config.get("DEFAULT_LOGIN_ID") or "").strip()
+    if not _is_placeholder_config(lid_raw):
+        login_id = lid_raw
+
+    if account_id:
+        return account_id, None
+    return None, login_id
+
+
+def _resolve_account_manager_main() -> str:
+    """解析 account-manager CLI 入口路径。
+
+    优先级：ACCOUNT_MANAGER_ROOT → get_sibling_skills_root → 开发机兜底。
+    末尾 dev 路径仅用于模板/本机调试，复制到真实 skill 后不要依赖个人机器绝对路径。
+    """
+    env_root = (config.get("ACCOUNT_MANAGER_ROOT") or os.getenv("ACCOUNT_MANAGER_ROOT") or "").strip()
+    if env_root and os.path.isfile(os.path.join(env_root, "scripts", "main.py")):
+        return os.path.join(os.path.abspath(env_root), "scripts", "main.py")
+
+    scripts_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+    skills_root = get_sibling_skills_root(scripts_dir)
+    candidate = os.path.join(skills_root, "account-manager", "scripts", "main.py")
+    if os.path.isfile(candidate):
+        return candidate
+
+    # 开发环境兜底：仅模板/本机调试；生产依赖宿主注入的路径变量，勿硬编码个人目录
+    dev = r"D:\OpenClaw\client-commons\account-manager\scripts\main.py"
+    if os.path.isfile(dev):
+        return dev
+
+    raise AccountManagerError(
+        "ACCOUNT_NOT_FOUND",
+        "未找到 account-manager，请配置 ACCOUNT_MANAGER_ROOT 或安装 account-manager 技能。",
+    )
+
+
+def _parse_last_json(stdout: str) -> Any:
+    lines = [ln.strip() for ln in (stdout or "").splitlines() if ln.strip()]
+    for raw in reversed(lines):
+        if raw.startswith("ERROR:"):
+            continue
+        try:
+            return json.loads(raw)
+        except json.JSONDecodeError:
+            continue
+    raise AccountManagerError("UNKNOWN_ERROR", "stdout 中没有可解析的 JSON。")
+
+
+def _run_argv(argv_suffix: List[str]) -> subprocess.CompletedProcess[str]:
+    main_py = _resolve_account_manager_main()
+    env = os.environ.copy()
+    return subprocess.run(
+        [sys.executable, main_py, *argv_suffix],
+        capture_output=True,
+        text=True,
+        encoding="utf-8",
+        errors="replace",
+        env=env,
+    )
+
+
+def _normalize_error_code(raw: str) -> str:
+    code = (raw or "").strip()
+    if code.startswith("ERROR:"):
+        code = code[6:]
+    return code
+
+
+def _validate_pick_payload(payload: dict[str, Any]) -> dict[str, Any]:
+    if not isinstance(payload, dict):
+        raise AccountManagerError("ACCOUNT_NOT_FOUND", "ensure-web 返回格式异常。")
+    if payload.get("success") is False:
+        err = payload.get("error") if isinstance(payload.get("error"), dict) else {}
+        code = _normalize_error_code(str(err.get("code") or ""))
+        message = str(err.get("message") or "")
+        if code == "LEASE_CONFLICT" or "LEASE_CONFLICT" in code:
+            raise AccountManagerError("LEASE_CONFLICT", message or LEASE_BUSY_MESSAGE)
+        if code == "AMBIGUOUS_ACCOUNT" or "AMBIGUOUS_ACCOUNT" in code:
+            raise AccountManagerError(
+                "AMBIGUOUS_ACCOUNT",
+                message or "匹配到多条账号，请改用数字 id 或更精确的登录标识。",
+            )
+        if code in ("NO_ACCOUNT", "ACCOUNT_NOT_FOUND") or "NO_ACCOUNT" in code:
+            raise AccountManagerError("NO_ACCOUNT", message or "没有可用账号。")
+        raise AccountManagerError(code or "ENSURE_WEB_FAILED", message or "ensure-web 失败。")
+
+    if not payload.get("profile_dir"):
+        raise AccountManagerError("ACCOUNT_NOT_FOUND", "ensure-web 返回的账号缺少 profile_dir。")
+    if not payload.get("lease_token"):
+        raise AccountManagerError("LEASE_REQUIRED", "account-manager 未返回 lease_token，禁止打开浏览器。")
+    return payload
+
+
+def _ensure_web_with_lease(
+    platform: str,
+    *,
+    login_id: Optional[str] = None,
+) -> Dict[str, Any]:
+    start_url = (config.get("TARGET_BASE_URL") or DEFAULT_START_URL).strip() or DEFAULT_START_URL
+    lid = (login_id or "").strip() or None
+    label = f"{platform} {lid}" if lid else DEFAULT_ACCOUNT_LABEL
+    argv = [
+        "account",
+        "ensure-web",
+        "--platform",
+        platform,
+        "--url",
+        start_url,
+        "--auth-strategy",
+        DEFAULT_AUTH_STRATEGY,
+        "--label",
+        label,
+        "--lease",
+        "--holder",
+        LEASE_HOLDER,
+        "--ttl-sec",
+        LEASE_TTL_SEC,
+        "--purpose",
+        "rpa",
+    ]
+    if lid:
+        argv.extend(["--login-id", lid])
+
+    proc = _run_argv(argv)
+    out = proc.stdout or ""
+    if proc.returncode != 0 and not out.strip():
+        raise AccountManagerError(
+            "ENSURE_WEB_FAILED",
+            (proc.stderr or "").strip() or "ensure-web 子进程失败",
+        )
+    payload = _parse_last_json(out)
+    if isinstance(payload, dict) and payload.get("success") is False:
+        return _validate_pick_payload(payload)
+    if not isinstance(payload, dict):
+        raise AccountManagerError("ACCOUNT_NOT_FOUND", "ensure-web 返回格式异常。")
+    return _validate_pick_payload(payload)
+
+
+def _pick_existing_with_lease(
+    platform: str,
+    *,
+    login_id: Optional[str] = None,
+    label: Optional[str] = None,
+) -> Dict[str, Any]:
+    argv = [
+        "account",
+        "pick-web",
+        "--platform",
+        platform,
+        "--lease",
+        "--holder",
+        LEASE_HOLDER,
+        "--ttl-sec",
+        LEASE_TTL_SEC,
+        "--purpose",
+        "rpa",
+    ]
+    if login_id:
+        argv.extend(["--login-id", login_id])
+    elif label:
+        argv.extend(["--label", label])
+    else:
+        raise AccountManagerError("AMBIGUOUS_ACCOUNT", "指定账号缺少可用于带租约选择的登录标识或名称。")
+
+    proc = _run_argv(argv)
+    out = proc.stdout or ""
+    if proc.returncode != 0 and not out.strip():
+        raise AccountManagerError(
+            "PICK_WEB_FAILED",
+            (proc.stderr or "").strip() or "pick-web 子进程失败",
+        )
+    payload = _parse_last_json(out)
+    return _validate_pick_payload(payload)
+
+
+def _pick_by_id_with_lease(platform: str, account_id: int) -> Dict[str, Any]:
+    proc = _run_argv(["account", "get", str(account_id)])
+    out = proc.stdout or ""
+    if proc.returncode != 0 or out.startswith("ERROR:"):
+        raise AccountManagerError("ACCOUNT_NOT_FOUND", f"指定账号 {account_id} 不存在或获取失败。")
+    raw = _parse_last_json(out)
+    if isinstance(raw, dict) and "data" in raw and isinstance(raw["data"], dict):
+        data = raw["data"]
+    elif isinstance(raw, dict):
+        data = raw
+    else:
+        raise AccountManagerError("ACCOUNT_NOT_FOUND", "account get 返回非对象 JSON。")
+
+    if data.get("success") is False:
+        raise AccountManagerError("ACCOUNT_NOT_FOUND", f"指定账号 {account_id} 不存在或获取失败。")
+    platform_key = str(data.get("platform_key") or "").lower()
+    if platform_key != platform.lower():
+        raise AccountManagerError(
+            "ACCOUNT_NOT_FOUND",
+            f"账号 {account_id} 不是 {platform} 平台账号。",
+        )
+    profile_dir = str(data.get("profile_dir") or "").strip()
+    if not profile_dir:
+        raise AccountManagerError("ACCOUNT_NOT_FOUND", f"账号 {account_id} 缺少 profile_dir。")
+    if str(data.get("status") or "active").lower() != "active":
+        raise AccountManagerError("ACCOUNT_NOT_FOUND", f"账号 {account_id} 当前不是 active 状态。")
+
+    try:
+        selected = _pick_existing_with_lease(
+            platform,
+            login_id=(str(data.get("login_id") or "").strip() or None),
+            label=(str(data.get("account_label") or "").strip() or None),
+        )
+    except AccountManagerError as exc:
+        if exc.code in ("NO_ACCOUNT", "ACCOUNT_NOT_FOUND"):
+            raise AccountManagerError("LEASE_CONFLICT", LEASE_BUSY_MESSAGE) from exc
+        raise
+    if str(selected.get("id")) != str(account_id):
+        release_lease(str(selected.get("lease_token") or ""))
+        raise AccountManagerError(
+            "AMBIGUOUS_ACCOUNT",
+            f"无法唯一取得指定账号 {account_id} 的租约，请检查重复的登录标识或账号名称。",
+        )
+    return selected
+
+
+def pick_web_account(
+    platform: str,
+    account_id: Optional[str] = None,
+    login_id: Optional[str] = None,
+) -> dict:
+    """获取网页账号（profile_dir + lease_token）。
+
+    优先级：数字 account_id → login_id（ensure-web --login-id）→ 按平台 ensure-web。
+    """
+    platform_key = (platform or PLACEHOLDER_PLATFORM).strip() or PLACEHOLDER_PLATFORM
+
+    aid_raw = (account_id or "").strip()
+    if aid_raw and not _is_placeholder_config(aid_raw):
+        if not aid_raw.isdigit():
+            if not (login_id or "").strip():
+                login_id = aid_raw
+            aid_raw = ""
+        else:
+            return _pick_by_id_with_lease(platform_key, int(aid_raw))
+
+    lid = (login_id or "").strip() or None
+    if lid and _is_placeholder_config(lid):
+        lid = None
+
+    try:
+        return _ensure_web_with_lease(platform_key, login_id=lid)
+    except AccountManagerError as exc:
+        if exc.code in ("NO_ACCOUNT", "ACCOUNT_NOT_FOUND") or "NO_ACCOUNT" in exc.code:
+            raise AccountManagerError("ACCOUNT_SETUP_REQUIRED", ACCOUNT_SETUP_MESSAGE) from exc
+        raise
+
+
+def release_lease(lease_token: Optional[str]) -> None:
+    token = (lease_token or "").strip()
+    if not token:
+        return
+    try:
+        proc = _run_argv(["lease", "release", token])
+        if proc.returncode != 0:
+            logger.warning("lease_release_failed stdout=%s", (proc.stdout or "").strip())
+    except Exception:
+        logger.warning("lease_release_exception", exc_info=True)

examples/real_browser_rpa/scripts/service/browser_session.py

@@ -0,0 +1,135 @@
+"""浏览器会话启动（系统 Chrome/Edge + Playwright persistent context）。"""
+
+from __future__ import annotations
+
+import logging
+import os
+from typing import Any, Optional, Tuple
+
+from util.constants import DEFAULT_START_URL
+
+logger = logging.getLogger(__name__)
+
+DEFAULT_PAGE_TIMEOUT_MS = 15_000
+GOTO_TIMEOUT_MS = 60_000
+
+STEALTH_INIT_SCRIPT = """
+(() => {
+  try { Object.defineProperty(navigator, 'webdriver', { get: () => undefined }); } catch (e) {}
+})();
+"""
+
+
+def get_start_url() -> str:
+    return (os.getenv("TARGET_START_URL") or DEFAULT_START_URL).strip() or DEFAULT_START_URL
+
+
+def _headless_from_env() -> bool:
+    v = (os.getenv("OPENCLAW_BROWSER_HEADLESS") or "0").strip().lower()
+    return v in ("1", "true", "yes", "on")
+
+
+def _find_chrome_executable() -> str | None:
+    try:
+        from jiangchang_skill_core.runtime_env import find_chrome_executable
+
+        chrome = find_chrome_executable()
+        if chrome and os.path.isfile(chrome):
+            return chrome
+    except ImportError:
+        pass
+
+    candidates = [
+        os.path.expandvars(r"%ProgramFiles%\Google\Chrome\Application\chrome.exe"),
+        os.path.expandvars(r"%ProgramFiles(x86)%\Google\Chrome\Application\chrome.exe"),
+        os.path.expandvars(r"%ProgramFiles%\Microsoft\Edge\Application\msedge.exe"),
+        os.path.expandvars(r"%ProgramFiles(x86)%\Microsoft\Edge\Application\msedge.exe"),
+    ]
+    for path in candidates:
+        if path and os.path.isfile(path):
+            return path
+    return None
+
+
+async def start_browser_session(
+    profile_dir: str,
+    *,
+    headless: Optional[bool] = None,
+) -> Tuple[Any, Any, Any]:
+    """
+    启动持久化 Chrome profile，new_page + goto 入口页，返回 (playwright, context, page)。
+
+    真实 skill 需要安装 playwright 与 jiangchang_skill_core。
+    """
+    from playwright.async_api import async_playwright
+
+    hl = headless if headless is not None else _headless_from_env()
+    start_url = get_start_url()
+    chrome = _find_chrome_executable()
+    if not chrome:
+        raise RuntimeError(
+            "ERROR:MISSING_BROWSER 未检测到 Chrome 或 Edge 浏览器，请先安装系统浏览器后重试。"
+        )
+
+    launch_args = ["--start-maximized", "--disable-blink-features=AutomationControlled"]
+    logger.info(
+        "browser_launch chrome=%s profile_dir=%s start_url=%s args=%s headless=%s",
+        chrome,
+        profile_dir,
+        start_url,
+        launch_args,
+        hl,
+    )
+    print(f"[浏览器] 系统 Chrome: {chrome}")
+    print(f"[浏览器] profile_dir: [{profile_dir}]")
+    print(f"[浏览器] startup_url={start_url}")
+    print(f"[浏览器] args={launch_args}")
+
+    pw = await async_playwright().start()
+    context = None
+    try:
+        context = await pw.chromium.launch_persistent_context(
+            user_data_dir=profile_dir,
+            headless=hl,
+            executable_path=chrome,
+            locale="zh-CN",
+            no_viewport=True,
+            args=launch_args,
+            ignore_default_args=["--enable-automation"],
+        )
+        await context.add_init_script(STEALTH_INIT_SCRIPT)
+
+        page = await context.new_page()
+        page.set_default_timeout(DEFAULT_PAGE_TIMEOUT_MS)
+
+        try:
+            await page.goto(start_url, wait_until="domcontentloaded", timeout=GOTO_TIMEOUT_MS)
+        except Exception as exc:
+            raise RuntimeError(
+                f"浏览器已启动，但未能打开目标首页 {start_url}。"
+                "请检查网络、Chrome profile、代理或页面访问状态。"
+                f"（{exc}）"
+            ) from exc
+
+        return pw, context, page
+    except Exception:
+        if context is not None:
+            try:
+                await context.close()
+            except Exception:
+                pass
+        await pw.stop()
+        raise
+
+
+async def close_browser_context(pw, context) -> None:
+    try:
+        if context is not None:
+            await context.close()
+    except Exception:
+        pass
+    try:
+        if pw is not None:
+            await pw.stop()
+    except Exception:
+        pass

examples/real_browser_rpa/scripts/service/human_verification.py

@@ -0,0 +1,450 @@
+"""人工验证等待：保存登录倒计时、滑块、短信验证码等（不自动破解）。"""
+
+from __future__ import annotations
+
+import asyncio
+import logging
+import random
+import re
+import time
+from dataclasses import dataclass
+from typing import Optional
+
+from util.constants import LOG_LOGGER_NAME
+
+logger = logging.getLogger(LOG_LOGGER_NAME)
+
+TEXT_EXCERPT_MAX = 120
+
+SAVE_LOGIN_STRONG_MARKERS = (
+    "是否保存登录信息",
+    "下次登录更便捷",
+    "保存登录信息",
+)
+
+SAVE_LOGIN_CONTAINER_SELECTORS = (
+    "[role=\"dialog\"]",
+    ".semi-modal",
+    ".semi-modal-content",
+)
+
+SLIDER_SELECTORS = [
+    ".vc-captcha-verify.slide",
+    ".captcha_verify_bar--title",
+    ".captcha-slider-tips",
+    "#captcha_verify_image",
+    ".captcha-slider-btn",
+]
+
+SMS_SELECTORS = [
+    ".second-verify-panel",
+    ".uc-ui-verify_sms-input",
+    ".uc-ui-verify-new_header-title",
+    "input[placeholder='手机号']",
+    "input[placeholder='请输入验证码']",
+]
+
+DIALOG_TEXT_CONTAINERS = [
+    "[role='dialog']",
+    ".semi-modal",
+    ".semi-modal-content",
+    ".vc-captcha-verify",
+    ".second-verify-panel",
+]
+
+RISK_MARKERS = (
+    "操作频繁",
+    "访问过于频繁",
+    "风险验证",
+    "安全验证",
+)
+
+
+@dataclass
+class HumanVerificationState:
+    present: bool
+    kind: str
+    message: str
+    selector: str = ""
+    text_excerpt: str = ""
+
+
+@dataclass
+class HumanVerificationWaitResult:
+    timed_out: bool
+    kind: str = ""
+    code: str = ""
+    message: str = ""
+    stage: str = ""
+
+
+def _text_excerpt(text: str) -> str:
+    cleaned = re.sub(r"\s+", " ", (text or "").strip())
+    if len(cleaned) <= TEXT_EXCERPT_MAX:
+        return cleaned
+    return cleaned[:TEXT_EXCERPT_MAX] + "..."
+
+
+def _contains_any(text: str, markers: tuple[str, ...]) -> bool:
+    return any(m in text for m in markers)
+
+
+async def _selector_visible(page, selector: str) -> bool:
+    try:
+        loc = page.locator(selector).first
+        return await loc.is_visible(timeout=500)
+    except Exception:
+        return False
+
+
+async def _selector_inner_text(page, selector: str) -> str:
+    try:
+        return await page.locator(selector).first.inner_text(timeout=1000)
+    except Exception:
+        return ""
+
+
+async def _visible_text_from_first_visible(page, selectors: tuple[str, ...] | list[str]) -> tuple[str, str]:
+    for sel in selectors:
+        try:
+            loc = page.locator(sel).first
+            if await loc.is_visible(timeout=500):
+                text = await loc.inner_text(timeout=1000)
+                return sel, text or ""
+        except Exception:
+            continue
+    return "", ""
+
+
+def _save_login_popup_from_text(text: str) -> bool:
+    if not text:
+        return False
+    if _contains_any(text, SAVE_LOGIN_STRONG_MARKERS):
+        return True
+    if "保存" in text and "取消" in text and ("登录" in text or "登录信息" in text):
+        return True
+    return False
+
+
+async def detect_save_login_popup(page) -> bool:
+    sel, text = await _visible_text_from_first_visible(page, SAVE_LOGIN_CONTAINER_SELECTORS)
+    if sel and _save_login_popup_from_text(text):
+        return True
+    return False
+
+
+async def wait_save_login_countdown_if_present(page, timeout_sec: int = 8) -> bool:
+    """若出现“保存登录信息”倒计时弹窗则等待其消失；未出现则立即返回 False。"""
+    if not await detect_save_login_popup(page):
+        return False
+
+    logger.info("save_login_popup_detected")
+    print("[登录] 检测到“保存登录信息”倒计时弹窗，等待其自动关闭...")
+    start = time.monotonic()
+    deadline = start + timeout_sec
+    while time.monotonic() < deadline:
+        if not await detect_save_login_popup(page):
+            elapsed = round(time.monotonic() - start, 2)
+            logger.info("save_login_popup_gone elapsed_sec=%s", elapsed)
+            return True
+        await asyncio.sleep(0.5)
+
+    elapsed = round(time.monotonic() - start, 2)
+    logger.warning(
+        "save_login_popup_still_visible elapsed_sec=%s timeout_sec=%s",
+        elapsed,
+        timeout_sec,
+    )
+    print(
+        f"[登录] 警告：保存登录信息弹窗超过 {timeout_sec} 秒仍未消失，"
+        "将继续后续流程（您可能已手工点击保存/取消）。"
+    )
+    return True
+
+
+async def detect_slider_verification(page) -> Optional[HumanVerificationState]:
+    sel_slide = ".vc-captcha-verify.slide"
+    if await _selector_visible(page, sel_slide):
+        text = await _selector_inner_text(page, sel_slide)
+        return HumanVerificationState(
+            present=True,
+            kind="slider",
+            message="滑块验证码",
+            selector=sel_slide,
+            text_excerpt=_text_excerpt(text),
+        )
+
+    sel_title = ".captcha_verify_bar--title"
+    if await _selector_visible(page, sel_title):
+        title_text = await _selector_inner_text(page, sel_title)
+        if "请完成下列验证后继续" in title_text:
+            return HumanVerificationState(
+                present=True,
+                kind="slider",
+                message="滑块验证码",
+                selector=sel_title,
+                text_excerpt=_text_excerpt(title_text),
+            )
+
+    sel_tips = ".captcha-slider-tips"
+    if await _selector_visible(page, sel_tips):
+        tips_text = await _selector_inner_text(page, sel_tips)
+        if "拖动完成上方拼图" in tips_text:
+            return HumanVerificationState(
+                present=True,
+                kind="slider",
+                message="滑块验证码",
+                selector=sel_tips,
+                text_excerpt=_text_excerpt(tips_text),
+            )
+
+    if await _selector_visible(page, "#captcha_verify_image"):
+        for btn_sel in (".captcha-slider-btn", ".captcha_verify_slide--button", ".captcha-slider"):
+            if await _selector_visible(page, btn_sel):
+                return HumanVerificationState(
+                    present=True,
+                    kind="slider",
+                    message="滑块验证码",
+                    selector=f"#captcha_verify_image+{btn_sel}",
+                    text_excerpt="",
+                )
+
+    return None
+
+
+async def detect_sms_verification(page) -> Optional[HumanVerificationState]:
+    sel_panel = ".second-verify-panel"
+    if await _selector_visible(page, sel_panel):
+        text = await _selector_inner_text(page, sel_panel)
+        return HumanVerificationState(
+            present=True,
+            kind="sms",
+            message="短信验证码",
+            selector=sel_panel,
+            text_excerpt=_text_excerpt(text),
+        )
+
+    sel_sms = ".uc-ui-verify_sms-input"
+    if await _selector_visible(page, sel_sms):
+        text = await _selector_inner_text(page, sel_sms)
+        return HumanVerificationState(
+            present=True,
+            kind="sms",
+            message="短信验证码",
+            selector=sel_sms,
+            text_excerpt=_text_excerpt(text),
+        )
+
+    sel_hdr = ".uc-ui-verify-new_header-title"
+    if await _selector_visible(page, sel_hdr):
+        hdr_text = await _selector_inner_text(page, sel_hdr)
+        if "短信验证" in hdr_text:
+            return HumanVerificationState(
+                present=True,
+                kind="sms",
+                message="短信验证码",
+                selector=sel_hdr,
+                text_excerpt=_text_excerpt(hdr_text),
+            )
+
+    phone_visible = await _selector_visible(
+        page,
+        ".second-verify-panel input[placeholder='手机号'], .uc-ui-verify_sms-input input[placeholder='手机号']",
+    )
+    code_visible = await _selector_visible(
+        page,
+        ".second-verify-panel input[placeholder='请输入验证码'], .uc-ui-verify_sms-input input[placeholder='请输入验证码']",
+    )
+    if phone_visible and code_visible:
+        return HumanVerificationState(
+            present=True,
+            kind="sms",
+            message="短信验证码",
+            selector="sms-phone-and-code-inputs",
+            text_excerpt="手机号+请输入验证码",
+        )
+
+    return None
+
+
+async def detect_human_verification_from_containers(page) -> Optional[HumanVerificationState]:
+    sel, text = await _visible_text_from_first_visible(page, DIALOG_TEXT_CONTAINERS)
+    if not sel or not text:
+        return None
+
+    if _contains_any(text, RISK_MARKERS):
+        return HumanVerificationState(
+            present=True,
+            kind="risk",
+            message="安全/频控验证",
+            selector=sel,
+            text_excerpt=_text_excerpt(text),
+        )
+
+    if sel in (".vc-captcha-verify", ".vc-captcha-verify-visibility"):
+        if "请完成下列验证后继续" in text or "拖动完成上方拼图" in text:
+            return HumanVerificationState(
+                present=True,
+                kind="slider",
+                message="滑块验证码",
+                selector=sel,
+                text_excerpt=_text_excerpt(text),
+            )
+
+    if sel in (".second-verify-panel", ".uc-ui-verify_sms-input"):
+        if "短信验证" in text or "获取验证码" in text:
+            return HumanVerificationState(
+                present=True,
+                kind="sms",
+                message="短信验证码",
+                selector=sel,
+                text_excerpt=_text_excerpt(text),
+            )
+
+    return None
+
+
+async def detect_human_verification(page) -> HumanVerificationState:
+    """主检测入口：仅在验证码/弹窗容器级检测，不扫整页 body。"""
+    state = await detect_slider_verification(page)
+    if state is not None:
+        return state
+    state = await detect_sms_verification(page)
+    if state is not None:
+        return state
+    state = await detect_human_verification_from_containers(page)
+    if state is not None:
+        return state
+    return HumanVerificationState(present=False, kind="", message="", selector="", text_excerpt="")
+
+
+def detect_human_verification_from_text(text: str) -> HumanVerificationState:
+    """
+    根据 HTML/容器文本判断验证弹窗（单元测试辅助，不能作为真实页面主检测入口）。
+    只检查验证容器 DOM 标记，不根据正文关键词误判。
+    """
+    html_lower = (text or "").lower()
+    has_slider_dom = (
+        "vc-captcha-verify" in html_lower
+        and "slide" in html_lower
+        and (
+            "captcha-slider-tips" in html_lower
+            or "captcha_verify_bar--title" in html_lower
+            or "captcha_verify_image" in html_lower
+        )
+    )
+    if has_slider_dom:
+        selector = ".vc-captcha-verify.slide"
+        if "captcha-slider-tips" in html_lower:
+            selector = ".captcha-slider-tips"
+        return HumanVerificationState(
+            present=True,
+            kind="slider",
+            message="滑块验证码",
+            selector=selector,
+            text_excerpt="",
+        )
+
+    has_sms_dom = "second-verify-panel" in html_lower or "uc-ui-verify_sms-input" in html_lower
+    if has_sms_dom:
+        selector = ".second-verify-panel" if "second-verify-panel" in html_lower else ".uc-ui-verify_sms-input"
+        return HumanVerificationState(
+            present=True,
+            kind="sms",
+            message="短信验证码",
+            selector=selector,
+            text_excerpt="",
+        )
+
+    return HumanVerificationState(present=False, kind="", message="", selector="", text_excerpt="")
+
+
+def _wait_log_message(state: HumanVerificationState, wait_sec: int) -> str:
+    if state.kind == "slider":
+        return f"[人工验证] 检测到滑块验证码，请在浏览器中手工完成，最多等待 {wait_sec} 秒..."
+    if state.kind == "sms":
+        return f"[人工验证] 检测到短信验证码，请在浏览器中手工完成，最多等待 {wait_sec} 秒..."
+    return f"[人工验证] 检测到安全验证，请在浏览器中手工处理，最多等待 {wait_sec} 秒..."
+
+
+def _timeout_error_code(kind: str) -> str:
+    if kind == "slider":
+        return "SLIDER_VERIFICATION_TIMEOUT"
+    if kind == "sms":
+        return "SMS_VERIFICATION_TIMEOUT"
+    return "HUMAN_VERIFICATION_TIMEOUT"
+
+
+def _timeout_error_message(kind: str, wait_sec: int) -> str:
+    if kind == "slider":
+        return (
+            f"滑块验证码未在 {wait_sec} 秒内完成，任务已停止。"
+            "请重新运行任务并及时在浏览器中完成验证。"
+        )
+    if kind == "sms":
+        return (
+            f"短信验证码未在 {wait_sec} 秒内完成，任务已停止。"
+            "请重新运行任务并及时完成短信验证。"
+        )
+    return (
+        f"安全验证未在 {wait_sec} 秒内完成，任务已停止。"
+        "请重新运行任务并及时在浏览器中完成验证。"
+    )
+
+
+async def wait_human_verification_if_present(
+    page,
+    *,
+    wait_sec: int = 180,
+    stage: str = "unknown",
+) -> Optional[HumanVerificationWaitResult]:
+    """
+    若存在人工验证则等待用户完成；无验证或已完成返回 None；超时返回 HumanVerificationWaitResult。
+    不自动拖动滑块、不自动填写短信验证码。
+    """
+    state = await detect_human_verification(page)
+    if not state.present:
+        return None
+
+    logger.warning(
+        "human_verification_detected stage=%s kind=%s selector=%s text=%s",
+        stage,
+        state.kind,
+        state.selector,
+        state.text_excerpt,
+    )
+    print(_wait_log_message(state, wait_sec))
+
+    last_state = state
+    start = time.monotonic()
+    deadline = start + wait_sec
+
+    while time.monotonic() < deadline:
+        state = await detect_human_verification(page)
+        if not state.present:
+            elapsed = round(time.monotonic() - start, 2)
+            logger.info(
+                "human_verification_passed stage=%s kind=%s elapsed_sec=%s",
+                stage,
+                last_state.kind,
+                elapsed,
+            )
+            await asyncio.sleep(random.uniform(1.0, 2.0))
+            return None
+        last_state = state
+        await asyncio.sleep(2.0)
+
+    logger.warning(
+        "human_verification_timeout stage=%s kind=%s wait_sec=%s selector=%s",
+        stage,
+        last_state.kind,
+        wait_sec,
+        last_state.selector,
+    )
+    return HumanVerificationWaitResult(
+        timed_out=True,
+        kind=last_state.kind,
+        code=_timeout_error_code(last_state.kind),
+        message=_timeout_error_message(last_state.kind, wait_sec),
+        stage=stage,
+    )

examples/real_browser_rpa/scripts/service/task_rpa.py

@@ -0,0 +1,637 @@
+"""真实网站关键词搜索 RPA 示例（async Playwright）。"""
+
+from __future__ import annotations
+
+import logging
+import os
+import random
+import re
+import time
+from dataclasses import dataclass, field
+from typing import Any, Callable, Dict, List, Optional, Tuple
+
+from jiangchang_skill_core import config
+from jiangchang_skill_core.activity import interruptible_sleep
+from jiangchang_skill_core.rpa import poll_until
+
+from service.browser_session import close_browser_context, get_start_url, start_browser_session
+from service.human_verification import (
+    HumanVerificationWaitResult,
+    wait_human_verification_if_present,
+    wait_save_login_countdown_if_present,
+)
+from util.constants import (
+    DEFAULT_MAX_ITEMS,
+    DEFAULT_MAX_SCROLLS,
+    DEFAULT_NO_NEW_ROUNDS_LIMIT,
+    HUMAN_WAIT_TIMEOUT,
+    LOG_LOGGER_NAME,
+    RESULT_CONTAINER_SELECTOR,
+    RESULT_END_TEXT,
+    RESULT_ITEM_SELECTOR,
+    SCROLL_CONTAINER_SELECTORS,
+    SEARCH_BUTTON_SELECTOR,
+    SEARCH_INPUT_SELECTORS,
+)
+from util.logging import mask_text, safe_log_value
+
+logger = logging.getLogger(LOG_LOGGER_NAME)
+
+
+@dataclass
+class ScrapeError:
+    code: str
+    message: str
+    browser_started: bool = False
+    stage: Optional[str] = None
+
+
+@dataclass
+class ScrapeRunResult:
+    success: bool
+    items: List[Dict[str, Any]] = field(default_factory=list)
+    stop_reason: Optional[str] = None
+    error: Optional[ScrapeError] = None
+
+
+StepCallback = Callable[[str], None]
+
+# 示例登录态 selector — 复制到新 skill 后必须用目标站点 F12/DOM 实测替换，禁止凭经验猜测或跨平台照抄
+LOGGED_IN_SELECTORS = (
+    "a[href*='/user/self']",
+    "[data-user-avatar]",
+    ".user-avatar",
+)
+LOGGED_OUT_SELECTOR = "button:has-text('登录')"
+
+
+def format_stop_reason_for_user(stop_reason: str | None, collected_count: int) -> str:
+    """将内部 stop_reason 枚举翻译为用户可理解的中文说明。"""
+    if stop_reason == "max_items":
+        return (
+            f"已达到本次默认采集规模（{collected_count} 条）。"
+            "如需更多，可以继续说「继续采集更多」或「尽量多采集」。"
+        )
+    if stop_reason == "end_marker":
+        return "页面提示没有更多结果，本次采集已完成。"
+    if stop_reason == "no_new_rounds":
+        return "连续多次加载没有发现新结果，本次采集已完成。"
+    if stop_reason == "max_scrolls":
+        return (
+            "已达到本次页面加载保护范围，本次采集已完成。"
+            "如需更深度采集，可以说明「尽量多采集」。"
+        )
+    if stop_reason == "human_verification_timeout":
+        return "人工验证未在规定时间内完成，任务已停止。"
+    return "本次采集已完成。"
+
+
+def _mask_account_ref(account: Dict[str, Any]) -> str:
+    for key in ("login_id", "phone", "mobile"):
+        raw = str(account.get(key) or "").strip()
+        if raw:
+            return mask_text(raw)
+    aid = account.get("id") or account.get("account_id")
+    if aid is not None:
+        return f"id:{aid}"
+    return "unknown"
+
+
+def _step_cb(cb: Optional[StepCallback], text: str) -> None:
+    if cb:
+        cb(text)
+
+
+async def _random_delay() -> None:
+    lo = max(0.0, config.get_float("STEP_DELAY_MIN", 1.0))
+    hi = max(lo, config.get_float("STEP_DELAY_MAX", 3.0))
+    await interruptible_sleep(random.uniform(lo, hi))
+
+
+async def _scroll_wait() -> None:
+    await interruptible_sleep(random.uniform(1.2, 3.5))
+
+
+def _headless() -> bool:
+    v = (os.getenv("OPENCLAW_BROWSER_HEADLESS") or "0").strip().lower()
+    return v in ("1", "true", "yes", "on")
+
+
+def _no_new_limit() -> int:
+    try:
+        return int(os.getenv("RPA_NO_NEW_ROUNDS_LIMIT") or str(DEFAULT_NO_NEW_ROUNDS_LIMIT))
+    except ValueError:
+        return DEFAULT_NO_NEW_ROUNDS_LIMIT
+
+
+async def _visible(locator) -> bool:
+    try:
+        return await locator.count() > 0 and await locator.is_visible(timeout=500)
+    except Exception:
+        return False
+
+
+async def _is_logged_out(page) -> bool:
+    try:
+        btn = page.locator(LOGGED_OUT_SELECTOR).first
+        return await _visible(btn)
+    except Exception:
+        return False
+
+
+async def _is_logged_in(page) -> bool:
+    if await _is_logged_out(page):
+        return False
+    for sel in LOGGED_IN_SELECTORS:
+        try:
+            loc = page.locator(sel).first
+            if await _visible(loc):
+                return True
+        except Exception:
+            continue
+    return False
+
+
+async def _open_login_panel_if_needed(page) -> None:
+    if not await _is_logged_out(page):
+        return
+    try:
+        btn = page.locator(LOGGED_OUT_SELECTOR).first
+        if await _visible(btn):
+            await btn.click()
+            await interruptible_sleep(random.uniform(1.0, 3.0))
+    except Exception:
+        pass
+
+
+async def _ensure_logged_in(page, *, wait_sec: int) -> None:
+    if await _is_logged_in(page):
+        return
+
+    await _open_login_panel_if_needed(page)
+    if await _is_logged_in(page):
+        return
+
+    print(f"[登录] 请在浏览器中完成登录，最多等待 {wait_sec} 秒...")
+    deadline = time.monotonic() + wait_sec
+    while time.monotonic() < deadline:
+        if await _is_logged_in(page):
+            print("[登录] 检测到登录成功")
+            return
+        await interruptible_sleep(2.0)
+
+    raise RuntimeError(
+        f"ERROR:LOGIN_TIMEOUT 浏览器已打开，但未完成登录。"
+        f"请重新运行任务并在浏览器打开后及时完成登录。"
+    )
+
+
+async def _find_search_input(page) -> Tuple[Optional[Any], str]:
+    for sel in SEARCH_INPUT_SELECTORS:
+        try:
+            loc = page.locator(sel)
+            count = await loc.count()
+            if count == 1 and await _visible(loc):
+                return loc, sel
+            if count > 1:
+                logger.warning("search_input_ambiguous selector=%s count=%s", sel, count)
+        except Exception:
+            continue
+
+    try:
+        ph = page.get_by_placeholder(re.compile("搜索"))
+        count = await ph.count()
+        if count == 1 and await ph.is_visible():
+            return ph, "placeholder=搜索"
+        if count > 1:
+            logger.warning("search_input_ambiguous selector=placeholder_search count=%s", count)
+    except Exception:
+        pass
+    return None, ""
+
+
+async def _find_search_button(page):
+    try:
+        btn = page.get_by_role("button", name="搜索")
+        count = await btn.count()
+        if count == 1 and await btn.is_visible():
+            return btn
+        if count > 1:
+            logger.warning("search_button_ambiguous selector=role_button_search count=%s", count)
+    except Exception:
+        pass
+    try:
+        btn = page.locator(SEARCH_BUTTON_SELECTOR)
+        count = await btn.count()
+        if count == 1 and await btn.is_visible():
+            return btn
+        if count > 1:
+            logger.warning(
+                "search_button_ambiguous selector=%s count=%s",
+                SEARCH_BUTTON_SELECTOR,
+                count,
+            )
+    except Exception:
+        pass
+    return None
+
+
+async def _wait_search_results(page, timeout_sec: float = 45.0) -> bool:
+    """有界等待搜索结果容器出现（kit poll_until；区分加载中与超时未就绪）。"""
+
+    async def _ready() -> bool:
+        try:
+            url = page.url or ""
+            if "/search" in url or "search" in url.lower():
+                if await page.locator(RESULT_CONTAINER_SELECTOR).count() > 0:
+                    return True
+        except Exception:
+            return False
+        return False
+
+    result = await poll_until(_ready, timeout_sec=timeout_sec, interval_sec=0.8)
+    return result.ok
+
+
+async def _has_end_marker(page) -> bool:
+    try:
+        container = page.locator(RESULT_CONTAINER_SELECTOR).first
+        if await container.count() > 0:
+            text = await container.inner_text(timeout=2000)
+            if RESULT_END_TEXT in text or "暂时没有更多了" in text:
+                return True
+    except Exception:
+        pass
+    try:
+        if await page.locator(f"text={RESULT_END_TEXT}").count() > 0:
+            return True
+    except Exception:
+        pass
+    return False
+
+
+async def _mouse_wheel_scroll(page) -> Tuple[str, int]:
+    wheel_delta = random.randint(650, 1200)
+    for sel in SCROLL_CONTAINER_SELECTORS:
+        loc = page.locator(sel)
+        try:
+            if await loc.count() > 0 and await loc.first.is_visible():
+                await loc.first.hover()
+                await _random_delay()
+                await page.mouse.wheel(0, wheel_delta)
+                return sel, wheel_delta
+        except Exception:
+            continue
+    await page.mouse.wheel(0, wheel_delta)
+    return "page", wheel_delta
+
+
+async def _parse_item_locator(item) -> Dict[str, Any]:
+    item_id = await item.get_attribute("data-item-id") or await item.get_attribute("id") or ""
+    title = ""
+    try:
+        title = (await item.inner_text(timeout=1000)).strip()[:200]
+    except Exception:
+        pass
+    return {
+        "item_id": item_id or title[:32] or str(id(item)),
+        "title": title,
+    }
+
+
+async def _collect_visible_items(page, seen_ids: set[str]) -> List[Dict[str, Any]]:
+    new_items: List[Dict[str, Any]] = []
+    try:
+        items = await page.locator(RESULT_ITEM_SELECTOR).all()
+    except Exception:
+        items = []
+    for item in items:
+        try:
+            parsed = await _parse_item_locator(item)
+            item_id = parsed.get("item_id")
+            if not item_id or item_id in seen_ids:
+                continue
+            seen_ids.add(str(item_id))
+            new_items.append(parsed)
+        except Exception:
+            continue
+    return new_items
+
+
+async def _count_visible_items(page) -> int:
+    try:
+        return await page.locator(RESULT_ITEM_SELECTOR).count()
+    except Exception:
+        return 0
+
+
+def _fail_result(error: ScrapeError, *, collected: int = 0) -> ScrapeRunResult:
+    logger.warning(
+        "rpa_failed code=%s stage=%s message=%s collected=%s",
+        error.code,
+        error.stage,
+        error.message,
+        collected,
+    )
+    return ScrapeRunResult(success=False, error=error)
+
+
+def _fail_on_verification_timeout(
+    verification_timeout: HumanVerificationWaitResult,
+    *,
+    collected: int = 0,
+) -> ScrapeRunResult:
+    return _fail_result(
+        ScrapeError(
+            code=verification_timeout.code,
+            message=verification_timeout.message,
+            browser_started=True,
+            stage=verification_timeout.stage or "unknown",
+        ),
+        collected=collected,
+    )
+
+
+async def run_keyword_search_async(
+    account: Dict[str, Any],
+    keyword: str,
+    *,
+    max_items: int = DEFAULT_MAX_ITEMS,
+    max_scrolls: int = DEFAULT_MAX_SCROLLS,
+    data_dir: str = "",
+    batch_id: str = "",
+    step_callback: Optional[StepCallback] = None,
+) -> ScrapeRunResult:
+    profile_dir = account.get("profile_dir") or ""
+    account_ref = _mask_account_ref(account)
+    wait_sec = int(os.getenv("HUMAN_WAIT_TIMEOUT") or str(HUMAN_WAIT_TIMEOUT))
+    no_new_limit = _no_new_limit()
+
+    logger.info(
+        "rpa_start keyword=%s max_items=%s max_scrolls=%s wait_sec=%s batch_id=%s account_ref=%s",
+        safe_log_value(keyword),
+        max_items,
+        max_scrolls,
+        wait_sec,
+        batch_id,
+        account_ref,
+    )
+
+    if not profile_dir:
+        err = ScrapeError(
+            "ACCOUNT_NOT_FOUND",
+            "账号缺少 profile_dir。",
+            browser_started=False,
+            stage="account_prepare",
+        )
+        return _fail_result(err)
+
+    pw = None
+    context = None
+    page = None
+    browser_started = False
+    collected_count = 0
+
+    try:
+        _step_cb(step_callback, "启动关键词搜索采集任务")
+        try:
+            pw, context, page = await start_browser_session(profile_dir, headless=_headless())
+        except RuntimeError as exc:
+            msg = str(exc)
+            err = ScrapeError(
+                "MISSING_BROWSER" if "MISSING_BROWSER" in msg else "UNKNOWN_ERROR",
+                msg.replace("ERROR:MISSING_BROWSER ", "").replace("ERROR:", ""),
+                browser_started="未能打开目标首页" in msg,
+                stage="browser_start" if "未能打开目标首页" in msg else "account_prepare",
+            )
+            return _fail_result(err)
+        browser_started = True
+
+        logger.info(
+            "browser_ready start_url=%s current_url=%s profile_dir_exists=%s",
+            get_start_url(),
+            page.url,
+            os.path.isdir(profile_dir),
+        )
+
+        _step_cb(step_callback, "打开目标站点首页")
+        await _random_delay()
+
+        verification_timeout = await wait_human_verification_if_present(
+            page, wait_sec=wait_sec, stage="browser_start"
+        )
+        if verification_timeout:
+            return _fail_on_verification_timeout(verification_timeout)
+
+        _step_cb(step_callback, "检查账号登录状态")
+        logger.info("login_check_start current_url=%s", page.url)
+        try:
+            await _ensure_logged_in(page, wait_sec=wait_sec)
+        except RuntimeError as exc:
+            msg = str(exc)
+            code = "LOGIN_TIMEOUT" if "LOGIN_TIMEOUT" in msg else "REQUIRE_LOGIN"
+            err = ScrapeError(
+                code,
+                msg.replace("ERROR:LOGIN_TIMEOUT ", "").replace("ERROR:", ""),
+                browser_started=True,
+                stage="login_check",
+            )
+            return _fail_result(err)
+        logger.info("login_check_done current_url=%s", page.url)
+
+        await wait_save_login_countdown_if_present(page)
+
+        verification_timeout = await wait_human_verification_if_present(
+            page, wait_sec=wait_sec, stage="login_check"
+        )
+        if verification_timeout:
+            return _fail_on_verification_timeout(verification_timeout)
+
+        _step_cb(step_callback, "定位搜索框")
+        search_input, input_selector = await _find_search_input(page)
+        if search_input is None:
+            err = ScrapeError(
+                "SEARCH_INPUT_NOT_FOUND",
+                "未找到搜索输入框。",
+                browser_started=True,
+                stage="search",
+            )
+            return _fail_result(err)
+        logger.info("search_input_found selector=%s", input_selector)
+
+        _step_cb(step_callback, f"输入关键词：{keyword}")
+        await search_input.click()
+        await _random_delay()
+        await page.keyboard.press("Control+A")
+        await page.keyboard.type(keyword, delay=random.randint(90, 240))
+        await _random_delay()
+
+        _step_cb(step_callback, "点击搜索")
+        search_btn = await _find_search_button(page)
+        search_method = "button"
+        if search_btn is not None:
+            await search_btn.click()
+        else:
+            search_method = "enter"
+            await page.keyboard.press("Enter")
+        logger.info(
+            "search_submitted keyword=%s method=%s current_url=%s",
+            safe_log_value(keyword),
+            search_method,
+            page.url,
+        )
+        await _random_delay()
+
+        verification_timeout = await wait_human_verification_if_present(
+            page, wait_sec=wait_sec, stage="search_verification"
+        )
+        if verification_timeout:
+            return _fail_on_verification_timeout(verification_timeout)
+
+        _step_cb(step_callback, "等待搜索结果")
+        if not await _wait_search_results(page):
+            verification_timeout = await wait_human_verification_if_present(
+                page, wait_sec=wait_sec, stage="search_results"
+            )
+            if verification_timeout:
+                return _fail_on_verification_timeout(verification_timeout)
+
+            if not await _wait_search_results(page, timeout_sec=10.0):
+                err = ScrapeError(
+                    "RESULT_CONTAINER_NOT_FOUND",
+                    "搜索结果未出现，且未检测到需要人工处理的验证码，请检查关键词或页面状态。",
+                    browser_started=True,
+                    stage="search",
+                )
+                return _fail_result(err)
+
+        container_count = await page.locator(RESULT_CONTAINER_SELECTOR).count()
+        logger.info(
+            "search_results_ready current_url=%s container_count=%s",
+            page.url,
+            container_count,
+        )
+
+        try:
+            await page.locator(RESULT_CONTAINER_SELECTOR).first.wait_for(state="visible", timeout=15_000)
+        except Exception:
+            err = ScrapeError(
+                "RESULT_CONTAINER_NOT_FOUND",
+                "搜索结果容器未出现。",
+                browser_started=True,
+                stage="search",
+            )
+            return _fail_result(err)
+
+        seen_ids: set[str] = set()
+        collected: List[Dict[str, Any]] = []
+        no_new_rounds = 0
+        stop_reason = "max_scrolls"
+        rounds_executed = 0
+
+        for scroll_round in range(max_scrolls + 1):
+            rounds_executed = scroll_round
+            _step_cb(step_callback, "读取当前结果列表")
+            visible_count = await _count_visible_items(page)
+            batch = await _collect_visible_items(page, seen_ids)
+            new_count = len(batch)
+            if batch:
+                collected.extend(batch)
+                no_new_rounds = 0
+            else:
+                no_new_rounds += 1
+
+            collected_count = len(collected)
+            end_marker = await _has_end_marker(page)
+            logger.info(
+                "collect_round round=%s max_scrolls=%s visible_count=%s new_count=%s "
+                "collected=%s no_new_rounds=%s no_new_limit=%s end_marker=%s current_url=%s",
+                scroll_round,
+                max_scrolls,
+                visible_count,
+                new_count,
+                collected_count,
+                no_new_rounds,
+                no_new_limit,
+                end_marker,
+                page.url,
+            )
+
+            if len(collected) >= max_items:
+                collected = collected[:max_items]
+                stop_reason = "max_items"
+                break
+
+            if end_marker:
+                stop_reason = "end_marker"
+                _step_cb(step_callback, "发现结果到底或达到采集数量")
+                break
+
+            if no_new_rounds >= no_new_limit:
+                stop_reason = "no_new_rounds"
+                logger.info(
+                    "collect_no_new_stop round=%s no_new_rounds=%s no_new_limit=%s collected=%s",
+                    scroll_round,
+                    no_new_rounds,
+                    no_new_limit,
+                    collected_count,
+                )
+                break
+
+            if scroll_round >= max_scrolls:
+                break
+
+            _step_cb(step_callback, "滚动加载更多结果")
+            scroll_target, wheel_delta = await _mouse_wheel_scroll(page)
+            logger.info(
+                "scroll round=%s target=%s wheel_delta=%s",
+                scroll_round,
+                scroll_target,
+                wheel_delta,
+            )
+            await _scroll_wait()
+
+            verification_timeout = await wait_human_verification_if_present(
+                page, wait_sec=wait_sec, stage="collect"
+            )
+            if verification_timeout:
+                return _fail_on_verification_timeout(
+                    verification_timeout,
+                    collected=collected_count,
+                )
+
+        logger.info(
+            "collect_stop reason=%s collected=%s rounds=%s no_new_rounds=%s",
+            stop_reason,
+            collected_count,
+            rounds_executed,
+            no_new_rounds,
+        )
+
+        if not collected:
+            err = ScrapeError(
+                "NO_RESULTS",
+                "未采集到任何结果。",
+                browser_started=True,
+                stage="collect",
+            )
+            return _fail_result(err, collected=0)
+
+        _step_cb(step_callback, "采集完成")
+        logger.info(
+            "rpa_success collected=%s stop_reason=%s",
+            len(collected[:max_items]),
+            stop_reason,
+        )
+        return ScrapeRunResult(success=True, items=collected[:max_items], stop_reason=stop_reason)
+
+    except Exception as exc:
+        err = ScrapeError(
+            "UNKNOWN_ERROR",
+            str(exc),
+            browser_started=browser_started,
+            stage="rpa",
+        )
+        return _fail_result(err, collected=collected_count)
+    finally:
+        await close_browser_context(pw, context)

examples/real_browser_rpa/scripts/service/task_service.py

@@ -0,0 +1,146 @@
+"""轻量任务编排示例（无真实数据库依赖）。"""
+
+from __future__ import annotations
+
+import asyncio
+import uuid
+from typing import Any, Optional
+
+from service.account_client import (
+    AccountManagerError,
+    pick_web_account,
+    release_lease,
+    resolve_account_selectors_from_config,
+)
+from service.task_rpa import (
+    ScrapeRunResult,
+    format_stop_reason_for_user,
+    run_keyword_search_async,
+)
+from util.constants import (
+    DEFAULT_MAX_ITEMS,
+    DEFAULT_MAX_SCROLLS,
+    SKILL_SLUG,
+    TARGET_PLATFORM,
+)
+
+
+def _error_payload(
+    code: str,
+    message: str,
+    *,
+    browser_started: Optional[bool] = None,
+    stage: Optional[str] = None,
+) -> dict[str, Any]:
+    payload: dict[str, Any] = {
+        "success": False,
+        "error": {"code": code, "message": message},
+    }
+    if browser_started is not None:
+        payload["browser_started"] = browser_started
+    if stage:
+        payload["stage"] = stage
+    return payload
+
+
+def _success_payload(
+    *,
+    keyword: str,
+    collected_count: int,
+    items: list[dict[str, Any]],
+    stop_reason: Optional[str],
+) -> dict[str, Any]:
+    return {
+        "success": True,
+        "skill": SKILL_SLUG,
+        "keyword": keyword,
+        "collected_count": collected_count,
+        "items": items,
+        "stop_reason": stop_reason,
+        "stop_reason_message": format_stop_reason_for_user(stop_reason, collected_count),
+    }
+
+
+async def run_keyword_search_task(
+    keyword: str,
+    *,
+    max_items: int = DEFAULT_MAX_ITEMS,
+    max_scrolls: int = DEFAULT_MAX_SCROLLS,
+    account_id: Optional[str] = None,
+    platform: str = TARGET_PLATFORM,
+) -> dict[str, Any]:
+    """
+    编排一次关键词搜索采集。
+
+    真实 skill 中还应：
+    - 写 SQLite 入库（items 表）
+    - 使用 RpaVideoSession 录制步骤留痕
+    - 失败时 capture_failure 截图
+    """
+    batch_id = uuid.uuid4().hex[:12]
+    data_dir = ""  # 示例占位；真实 skill 使用 get_skill_data_dir()
+    lease_token: Optional[str] = None
+    account: Optional[dict[str, Any]] = None
+
+    try:
+        cfg_account_id, cfg_login_id = resolve_account_selectors_from_config()
+        account = pick_web_account(
+            platform,
+            account_id=account_id or cfg_account_id,
+            login_id=cfg_login_id,
+        )
+        lease_token = account.get("lease_token")
+
+        scrape_result: ScrapeRunResult = await run_keyword_search_async(
+            account,
+            keyword,
+            max_items=max_items,
+            max_scrolls=max_scrolls,
+            data_dir=data_dir,
+            batch_id=batch_id,
+        )
+
+        if not scrape_result.success:
+            err = scrape_result.error
+            return _error_payload(
+                err.code if err else "UNKNOWN_ERROR",
+                err.message if err else "未知错误",
+                browser_started=err.browser_started if err else True,
+                stage=err.stage if err else "rpa",
+            )
+
+        collected_count = len(scrape_result.items)
+        return _success_payload(
+            keyword=keyword,
+            collected_count=collected_count,
+            items=scrape_result.items[:10],
+            stop_reason=scrape_result.stop_reason,
+        )
+    except AccountManagerError as exc:
+        return _error_payload(
+            exc.code,
+            exc.message,
+            browser_started=False,
+            stage="account_prepare",
+        )
+    finally:
+        release_lease(lease_token)
+
+
+def run_keyword_search_task_sync(
+    keyword: str,
+    *,
+    max_items: int = DEFAULT_MAX_ITEMS,
+    max_scrolls: int = DEFAULT_MAX_SCROLLS,
+    account_id: Optional[str] = None,
+    platform: str = TARGET_PLATFORM,
+) -> dict[str, Any]:
+    return asyncio.run(
+        run_keyword_search_task(
+            keyword,
+            max_items=max_items,
+            max_scrolls=max_scrolls,
+            account_id=account_id,
+            platform=platform,
+        )
+    )

examples/real_browser_rpa/scripts/util/constants.py

@@ -0,0 +1,31 @@
+"""示例常量（复制到新 skill 时请替换为目标站点与业务字段）。"""
+
+SKILL_SLUG = "example-real-browser-rpa"
+LOG_LOGGER_NAME = "openclaw.skill.example_real_browser_rpa"
+
+TARGET_PLATFORM = "target_platform"
+LEASE_HOLDER = "example-real-browser-rpa"
+LEASE_TTL_SEC = "1800"
+
+DEFAULT_START_URL = "https://example.com"
+DEFAULT_MAX_ITEMS = 100
+DEFAULT_MAX_SCROLLS = 40
+DEFAULT_NO_NEW_ROUNDS_LIMIT = 5
+HUMAN_WAIT_TIMEOUT = 180
+
+RESULT_END_TEXT = "没有更多结果了"
+
+# 示例 selector — 复制到新 skill 时按目标站点 DOM 替换
+SEARCH_INPUT_SELECTORS = (
+    'input[type="search"]',
+    'input[name="q"]',
+    'input[placeholder*="搜索"]',
+)
+SEARCH_BUTTON_SELECTOR = 'button:has-text("搜索")'
+RESULT_CONTAINER_SELECTOR = "#search-result-container"
+RESULT_ITEM_SELECTOR = "[data-result-item]"
+SCROLL_CONTAINER_SELECTORS = (
+    "#search-result-container",
+    ".search-result-scroll",
+    ".route-scroll-container",
+)

examples/real_browser_rpa/scripts/util/logging.py

@@ -0,0 +1,34 @@
+"""示例结构化日志工具。"""
+
+from __future__ import annotations
+
+import logging
+import re
+from typing import Any
+
+from util.constants import LOG_LOGGER_NAME
+
+
+def get_logger(name: str | None = None) -> logging.Logger:
+    return logging.getLogger(name or LOG_LOGGER_NAME)
+
+
+def mask_text(value: str, *, keep_start: int = 2, keep_end: int = 2) -> str:
+    s = (value or "").strip()
+    if len(s) >= 11 and s.isdigit():
+        return s[:3] + "****" + s[-4:]
+    if len(s) > keep_start + keep_end:
+        return s[:keep_start] + "****" + s[-keep_end:]
+    return "****"
+
+
+def safe_log_value(value: Any) -> str:
+    if value is None:
+        return ""
+    text = str(value)
+    if re.fullmatch(r"\d{7,}", text):
+        return mask_text(text)
+    if "@" in text and len(text) > 6:
+        local, _, domain = text.partition("@")
+        return f"{mask_text(local, keep_start=1, keep_end=1)}@{domain}"
+    return text